Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to conditional or situational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aqu
    -0.15
    ést
    -0.14
    enic
    -0.14
     voks
    -0.14
    wit
    -0.14
    hips
    -0.14
    ubu
    -0.14
    utches
    -0.14
    idel
    -0.13
    δεÏĤ
    -0.13
    POSITIVE LOGITS
    leneck
    0.15
     accompagn
    0.15
    ilee
    0.15
    å¥Ī
    0.14
     tá»ĩ
    0.14
    .matcher
    0.14
    ula
    0.14
    ẩu
    0.14
     Pou
    0.14
     Jackson
    0.14
    Act Density 0.019%

    No Known Activations